Shuffleboard: slide the puck into an unreachable zone

A two-finger parallel gripper hangs over a table (a floating gripper, no arm; it cannot rotate). x points to the right as seen from the front of the table, y away from the front (toward the back of the table), z up; the table top is at z = 0 and spans x from -0.35 to 0.35 and y from -0.30 to 0.30. The gripper's tool point can reach x in [-0.34, 0.34], y in [-0.27, 0.28], z in [0.012, 0.35]. The fingers close along the y axis; the fully open gap is 10 cm.

Goal: Slide the red puck along the slippery lane so that it comes to rest inside the blue zone. The lane is a smooth white slab 24 cm wide (x from -0.12 to 0.12) and 4 mm thick whose surface is very slippery (friction coefficient about 0.03 against the pucks); it runs from y = -0.25 past the back edge of the table and ends in mid-air at y = 0.85. A puck that slides past the end falls off. The gripper can only reach y <= 0.28, so the zone (the blue rectangle painted on the lane, x from -0.10 to 0.10, y from 0.44 to 0.62) cannot be reached: a puck must be pushed so that it slides there by itself, and a puck that stops beyond y = 0.28 can never be touched again. Each puck is a disc 5 cm across and 2 cm thick. Success is judged after robo done: the puck's centre must be inside the zone, resting on the lane and no longer moving.

What robo observe shows

• hand_pos: the gripper's tool point (between the fingertips), metres. gripper_open: 0 = closed, 1 = fully open (10 cm gap). holding: names of objects currently touching the fingers.
• objects: every movable object by name, with kind, color, pos (centre, metres), size (full x/y/z extent in its own frame), yaw_deg, half_height (current half extent along z), tilt_deg (0 = upright).
• fixtures: static things by name (pads, bowls, trays, plates, sockets, the drawer cabinet, the lane) with their positions and sizes. Pads are flat coloured squares on the table; bowls and trays have a floor_z and a rim_z.

Gripper

The grip value is a finger position target, not a hold command: +1 = fully closed, -1 = fully open (10 cm gap), and values in between give a partial opening (finger gap = 10 cm * (1 - G) / 2, so 0 = half open, a 5 cm gap). There is no separate "hold" value: to keep holding an object, keep sending +1 (the fingers then squeeze it). robo move-to X Y Z --grip G applies G on every step of the move, starting with the first, so --grip 1 closes the fingers at the start of the move (they take about 15 steps to close fully); without --grip, the last grip value is kept. robo grip G --steps N holds the hand still for N steps while applying G. The same values apply to the GRIP argument of robo act.

Task rules

• Skills are disabled on this task: robo move-to and robo grip return an error. Use robo act DX DY DZ GRIP only (DX/DY/DZ move the tool point by about 1 cm per unit per step; GRIP +1 closes, -1 opens, values in between give a partial opening: finger gap = 10 cm * (1 - GRIP) / 2).
• robo act --repeat N is limited to N <= 5 on this task (larger values are cut to 5).
• Step budget: 650 simulated steps (one step = 20 ms). Wall-clock limit: 20 minutes.
• Objects must be released (not touching the fingers) when the episode is judged, about 10 steps after robo done.